© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6177
    Prev
    Next
    INDEX
    Explanations

    stock market news and analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    涯
    -0.08
    vert
    -0.08
    ersive
    -0.08
    ä¸Ńå¼ı
    -0.08
    _CSR
    -0.08
     Rudy
    -0.08
    efined
    -0.08
    istra
    -0.08
    SWEP
    -0.08
    æĵħ
    -0.08
    POSITIVE LOGITS
    èĤ¡ä»·
    0.14
    åŁºæľ¬éĿ¢
    0.12
    æ¯ıèĤ¡
    0.11
    羸
    0.10
    æ¯Ľ
    0.10
    è·Łéļı
    0.10
    åĢ¼å¾Ĺåħ³æ³¨
    0.10
    èĤ¡ä¸ľå¤§ä¼ļ
    0.09
    ä¸ļ绩
    0.09
     currently
    0.09
    Activations Density 0.041%

    No Known Activations